Welcome to Convex Optimization, Game Theory, and Machine Learning for Upcoming 6G Networks

Description: Nowadays, wireless networks have faced an explosive growth of data traffic because of the dramatic increase in the use of mobile devices and, consequently, data-greedy and delay-sensitive applications. Furthermore, bringing everyone and everything unconnected to the connected world is crucial. Thus, researchers in both industry and academia have introduced various promising technologies, such as aerial networks, integrated space-air-ground (ISAG) networks, and reconfigurable intelligent surfaces (RIS)(both active and passive RISs)-assisted wireless networks, simultaneously transmission and reflection (STAR) RIS-assisted wireless networks, integrated sensing and communication (ISAC), and semantic communication, to fulfill the traffic demands and provide the seamless wireless connectively in the upcoming generation of wireless networks (i.e., 6G networks). However, we must overcome several research challenges, e.g., how to integrate non-terrestrial networks with the existing terrestrial networks not only to provide seamless wireless connectivity but also to improve the spectrum and energy efficiency in the ISAG networks, how to design optimal phase-shift in the RIS- and STAR-RIS-assisted wireless networks, how to integrate communication and sensing function in the same infrastructure, how to optimize beamforming design, and how to optimize the spectrum allocation between these two functions in ISAC, and among others, before deploying those technologies in the real world. Fortunately, methodologies such as convex optimization, game theory, and machine learning algorithms will help us to overcome challenges. Thus, in this course, we first comprehensively review the technologies appearing in 6G networks. Secondly, we give the theory background of convex optimization, game theory, and machine learning algorithms. Finally, we discuss how to implement those algorithms for cross-layer design optimization in the technologies appearing in 6G networks.

Prerequisites: The students must have the basic knowledge of linear algebra, probability and statistics, ordinary differential equations (ODE), partial differential equations (PDE), and wireless networking.

Learning objectives: The main objective is to introduce the technologies appearing in 6G networks and use convex optimization, game theory, and machine learning algorithms for cross-layer design optimization in the technologies appearing in 6G networks.

Organizer: Yan Kyaw Tun

Lecturers: Yan Kyaw Tun

ECTS: 3.0

Time: 23-25 June 2025

Place: Aalborg University (Room: TBA)

Zip code: 9220

City: Aalborg

Maximal number of participants: 30

Deadline: 2 June 2025

Disclaimer:
DDSA has explicit permission from Arcanic and the owners of the https://phdcourses.dk/ website to display the courses on ddsa.dk.